Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eaeff53af90b0a1a5dbaa9c97d687c722cb11487b72009c5477d5e81e8eb8cc4
+oid sha256:78ea7064c6307986e3d2a54ac14e8b7a4f7f6268ca0a9d720a64815b82d02926
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bdc2afec81cc3e56b8bba172990f787373bd2a3a6dd23da24fea4ddc638ccdb
+oid sha256:16dbb230fa6f9feb5bc3b591f3de6177d45fdb53f0484cfcc14f6d42ba3aad8c
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5c45a9d7925934b5907674a393a06a441b92cdf4c94dcc2de8c5597b2978120
+oid sha256:8492e33e7dfae4e0d5c2e2897a2d6f1e8e27b916ff8304725e653f24b34c4132
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.9884905815124512,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.028540849090260435,
+  "best_metric": 1.9812061786651611,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.042811273635390654,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 8.893,
       "eval_steps_per_second": 2.231,
       "step": 20
+    },
+    {
+      "epoch": 0.029967891544773455,
+      "grad_norm": 1.08573579788208,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 8.3976,
+      "step": 21
+    },
+    {
+      "epoch": 0.03424901890831252,
+      "grad_norm": 0.5004927515983582,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 8.3142,
+      "step": 24
+    },
+    {
+      "epoch": 0.03567606136282554,
+      "eval_loss": 1.98249351978302,
+      "eval_runtime": 66.0005,
+      "eval_samples_per_second": 8.939,
+      "eval_steps_per_second": 2.242,
+      "step": 25
+    },
+    {
+      "epoch": 0.038530146271851584,
+      "grad_norm": 0.6029341816902161,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 8.2691,
+      "step": 27
+    },
+    {
+      "epoch": 0.042811273635390654,
+      "grad_norm": 0.584296464920044,
+      "learning_rate": 0.0,
+      "loss": 7.9651,
+      "step": 30
+    },
+    {
+      "epoch": 0.042811273635390654,
+      "eval_loss": 1.9812061786651611,
+      "eval_runtime": 66.0349,
+      "eval_samples_per_second": 8.935,
+      "eval_steps_per_second": 2.241,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.613858577416192e+16,
+  "total_flos": 3.5450456956207104e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null